Multimedia Tools and Applications

, Volume 78, Issue 14, pp 19877–19903 | Cite as

Trajectory based abnormal event detection in video traffic surveillance using general potential data field with spectral clustering

  • J. Joshan AthanesiousEmail author
  • S. Sibi Chakkaravarthy
  • S. Vasuhi
  • V. Vaidehi


Detection of abnormal trajectories in a traffic scene is an important problem in Video Traffic Surveillance (VTS). Recently, General Potential Data Field (GPDf)-based trajectory clustering scheme has been adopted for detecting abnormal events such as illegal U-turn, wrong side and unusual driving behaviors and it uses spatial and temporal attributes explicitly. The concept of data field is used to discover the relation between the spatial points in data-space and grouping them into clusters based on their mutual interaction. Existing methodologies related to potential data field-based clustering have certain limitations such as pre-defined cluster size, non-effective cluster center identification, and limitation in range estimation using isotropic impact factor (h) which leads to inaccurate results. In order to address the above-mentioned issues, this paper proposes an efficient anomaly detection scheme based on General Potential Data field with Spectral Clustering (GPDfSC). The proposed GPDfSC scheme utilizes potential data field technique along with spectral clustering for effective identification of abnormalities. The Limitation in impact factor(h) is overcome by using anisotropic impact parameter Bmat. Further, Bayesian Decision theory is used to classify the events as normal or abnormal. The proposed scheme is implemented in real time using GPU and from the results it is found that it gives 12% better accuracy in detecting abnormalities than the state of art technique.


General potential data field Impact factor matrix Spatial trajectory data Dynamic time warping Spectral clustering Abnormal detection 



The first author extends his sincere gratitude to Anna university for supporting this research through Anna Centenary Research Fellowship (ACRF) and also grateful to Dr. R. Balasubramanian and Dr. Partha Pratim Roy from IIT-Roorkee for their valuable inputs and suggestions.


  1. 1.
    Ashok Kumar PM, Vaidehi V (2015) Anomalous event detection in traffic video based on sequential temporal patterns of spatial interval events. KSII Trans Internet Inform Syst 9(1):169–189. Google Scholar
  2. 2.
    Batapati P, Tran D, Sheng W, Liu M, Zeng R (2014) Video analysis for traffic anomaly detection using support vector machines. 1th World Congress on Intelligent Control and Automation: 5500–5505. doi:
  3. 3.
    Berndt DJ, Clifford J (1994) Using dynamic time warping to find patterns in time series. KDD workshop 10(16):359–370Google Scholar
  4. 4.
    Bhattacharyya A (1943) On a measure of divergence between two statistical populations defined by their probability distributions. Bull Calcutta Math Soc 35:99–109MathSciNetzbMATHGoogle Scholar
  5. 5.
    Blatt FJ (1986) Principles of physics (2nd ed.). published: Allyn and Bacon, BostonGoogle Scholar
  6. 6.
    Cai Y, Wang H, Chen X, Jiang H (2015) Trajectory-based anomalous behavior detection for intelligent traffic surveillance. IET Intell Transp Syst 9(8):810–816. CrossRefGoogle Scholar
  7. 7.
    Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey. ACM computing surveys (CSUR) 41(3):1–15. CrossRefGoogle Scholar
  8. 8.
    Cyert RM, DeGroot MH (1987) Bayesian decision theory. In: Bayesian analysis and uncertainty in economic theory. Springer, DordrechtGoogle Scholar
  9. 9.
    Determine the optimal number of cluster. Accessed 26 October 2017
  10. 10.
    Djalalov M, Nisar H, Salih Y, Malik AS (2010) An algorithm for vehicle detection and tracking. In Intelligent and Advanced Systems (ICIAS): 1–5. doi:
  11. 11.
    Douglas DH, Peucker TK (1973) Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica: Int J Geograph Inform Geo Visual 10(2):112–122. CrossRefGoogle Scholar
  12. 12.
    Fang M, Wang S, Jin H (2010) Spatial neighborhood clustering based on data field. Int Conf Adv Data Mining Applic 6440:262–269. CrossRefGoogle Scholar
  13. 13.
    Fu Z, Hu W, Tan T (2005) Similarity based vehicle trajectory clustering and anomaly detection. IEEE Int Conf Image Process 2:602–605. Google Scholar
  14. 14.
    Horova I, Kolacek J, Vopatova K (2013) Full bandwidth matrix selectors for gradient kernel density estimate. Comput Stat Data Anal 57(1):364–376. MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. IEEE Trans Syst Man Cybern Part C Appl Rev 34(3):334–352. CrossRefGoogle Scholar
  16. 16.
    Hung MH, Pan JS, Hsieh CH (2010) Speed up temporal median filter for background subtraction. 2010 First International Conference on In Pervasive Computing Signal Processing and Applications (PCSPA), 297–300. IEEEGoogle Scholar
  17. 17.
    iLIDS datasets. Accessed on May 2017/Google Scholar
  18. 18.
    Jiang F, Wu Y, Katsaggelos AK (2009) A dynamic hierarchical clustering method for trajectory-based unusual video event detection. IEEE Trans Image Process 18(4):907–913. MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Jiang F, Yuan J, Tsaftaris SA, Katsaggelos AK (2011) Anomalous video event detection using spatiotemporal context. Comput Vis Image Underst 115(3):323–333. CrossRefGoogle Scholar
  20. 20.
    Jung CR, Hennemann L, Musse SR (2008) Event detection using trajectory clustering and 4-D histograms. IEEE Trans Circuits Syst Video Technol 18(11):1565–1575. CrossRefGoogle Scholar
  21. 21.
    Kumar PA, Vaidehi V (2017) A transfer learning framework for traffic video using neuro-fuzzy approach. Sadhana 42(9):1431–1442. CrossRefGoogle Scholar
  22. 22.
    Kumar PA, Sathya V, Vaidehi V (2015) Traffic rule violation detection in traffic video surveillance. Int J Comput Sci Electron Eng (IJCSEE) 3(4):301–307Google Scholar
  23. 23.
    Laxhammar R, Falkman G (2014) Online learning and sequential anomaly detection in trajectories. IEEE Trans Pattern Anal Mach Intell 36(6):1158–1173. CrossRefzbMATHGoogle Scholar
  24. 24.
    Li D, Du Y (2007) Artificial intelligence with uncertainty. Chapman and Hall/CRC 193–211Google Scholar
  25. 25.
    Li D, Wang S, Gan W, Li D (2011) Data field for hierarchical clustering. Int J Data Warehouse Min 7(4):43–63. CrossRefGoogle Scholar
  26. 26.
    Liu YH, Chen WQ (2011) Line simplification algorithm implementation and error analysis. IEEE International Conference on Computer Science and Automation Engineering 64–68. doi:
  27. 27.
    Liu Y, Jin J, Zhang Y, Xu C (2014) A new clustering algorithm based on data field in complex networks. J Supercomput 67(3):723–737. CrossRefGoogle Scholar
  28. 28.
    Meng H-D, Wu P-F, Song Y-C, Xu G-D (2013) Research of clustering algorithm based on different data field model. Trans Tech Public 760-762:1925–1929. Google Scholar
  29. 29.
    Morris BT, Trivedi MM (2011) Trajectory learning for activity understanding: unsupervised, multilevel, and long-term adaptive approach. IEEE Trans Pattern Anal Mach Intell 33(11):2287–2301. CrossRefGoogle Scholar
  30. 30.
    Ng AY, Jordan MI, Weiss Y (2002) On spectral clustering: analysis and an algorithm. Adv Neural Inf Proces Syst: 849–856.Google Scholar
  31. 31.
  32. 32.
    Ranjith R, Athanesious JJ, Vaidehi V (2015) Anomaly detection using DBSCAN clustering technique for traffic video surveillance. In Advanced Computing (ICoAC), Seventh International Conference.1–6. IEEE. doi:
  33. 33.
    Sheather SJ (2004) Density estimation. Instit Math Stat 19(4):588–597. zbMATHGoogle Scholar
  34. 34.
    Wan Y, Yang TI, Keathly D, Buckles B (2014) Dynamic scene modelling and anomaly detection based on trajectory analysis. IET Intell Transp Syst 8(6):526–533. CrossRefGoogle Scholar
  35. 35.
    Wand MP, Jones MC (1995) Kernel smoothing. Number 60 in monographs on statistics and applied probability. Chapman & Hall/CRCGoogle Scholar
  36. 36.
    Wang X, Ma KT, Ng GW, Grimson WE (2011) Trajectory analysis and semantic region modeling using nonparametric hierarchical bayesian models. Int J Comput Vis1;95(3):287–312. doi:
  37. 37.
    Wang S, Li Y, Wang D (2016) Data field for mining big data. Geo-spatial Inform Sci 19(2):106–118. CrossRefGoogle Scholar
  38. 38.
    Wang S, Wang S, Yuan H, Li Q, Geng J, Yu Y (2018) Clustering by differencing potential of data field. Computing 100(4):403–419. MathSciNetCrossRefzbMATHGoogle Scholar
  39. 39.
    Zhang T, Liu S, Xu C, Lu H (2013) Mining semantic context information for intelligent video surveillance of traffic scenes. IEEE Trans Indust Inform 9(1):149–160. CrossRefGoogle Scholar
  40. 40.
    Zhao P, Qin K, Ye X, Wang Y, Chen Y (2017) A trajectory clustering approach based on decision graph and data field for detecting hotspots. Int J Geogr Inf Sci 3(6):1101–1127. Google Scholar
  41. 41.
    Zhou Y, Yan S, Huang TS (2007) Detecting anomaly in videos from trajectory similarity analysis. Multimedia and Expo IEEE International Conference 1087–1090. doi:

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Electronics EngineeringMadras Institute of TechnologyChennaiIndia
  2. 2.School of Computing Science and EngineeringVIT UniversityChennaiIndia

Personalised recommendations